An official music video created entirely with Veo 3! We collaborated with Google to produce a music video for the queen of Turkish pop, affectionately known as the “Little Sparrow.” On the 50th anniversary of her artistic career, we crafted this video using only Veo 3 and

I gave two talks #CVPR2025 #cvpr2025 Slides are now available for those interested 1- Catch me if you can: Manoeuvre the Competition with Your Unique Abilities tinyurl.com/StandOut-DD2025 2- Beyond Long Video Understanding tinyurl.com/BeyondLong-DD2…

📢 Applications open for a postdoc position in my group University of Bristol #MaVi on Video Understanding with 3D knowledge - DL 16 July jobs.ac.uk/job/DNQ703/res…

Winners of the EgoVis 2023/2024 Distinguished Paper Awards 🥇 are now available online: egovis.github.io/awards/2023_20… Watch the acceptance speeches here: youtu.be/Qbvg-s1bZLQ

Happy Canada Day! 🇨🇦 It’s Canada’s birthday 🎂 I’m so thankful to be Canadian. My parents immigrated from Greece in the early ’70s with little education and no English. My dad (miss you) was the son of a sheepherder, and my mom grew up on a small farm. In Canada, my dad started

We made a @gradio demo for AllTracker! AllTracker is the current state-of-the-art for general-purpose point tracking. The demo gives a good sense of the accuracy---try your own videos and see for yourself! 🔗 Demo: huggingface.co/spaces/aharley… 💻 Code: github.com/aharley/alltra…

Was a pleasure to visit #Iceland for 1st time, and give a keynote at #SCIA2025 on Opportunities in Egocentric Video Understanding. 🙏 to organizers Vedrana Andersen Dahl Serge Belongie Rasmus Larsen,Thomas Moeslund for the invitation. Enjoyed catching up with friends and making new ones.

Looking forward to the exciting week ahead... Thanks Giovanni M Farinella Roberto Cipolla Antonino Furnari for the invite! Already enjoyed our first dinner with Daniel Cremers TUM Computer Vision Group and Gerard Pons-Moll &co

Great talk yesterday by Dima Damen @ICVSS2025 on the past, present, and future of egocentric video! Video understanding out of the frame was especially exciting, pushing us to consider the 3D world beyond the camera's view. Now on to day 2! #ICVSS2025

How to make 3D fundamental to all aspects of computer vision? A Vedaldi Visual Geometry Group (VGG) with a brilliant tutorial this morning ICVSS #icvss2025

Scaling 4D Representations – new preprint arxiv.org/abs/2412.15212 and models now available github.com/google-deepmin…

The 3rd Perception Test challenge is now accepting submissions perception-test-challenge.github.io ! Prizes of up to 50k EUR across Perception Test tracks are available. The winners will be announced at the Perception Test workshop at #ICCV2025. Submission deadline: October 6, 2025.

Exciting news for students in India🇮🇳: get your free Google Gemini App Pro plan for 1 year! This gives you higher rate access to all our best models: 2.5 Pro, Veo 3, Deep Research, NotebookLM, and 2TB storage. Claim it at goo.gle/freepro - enjoy!